Pith. sign in

REVIEW 1 cited by

Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2205.07069 v1 pith:BFUH5PBJ submitted 2022-05-14 math.ST math.OCmath.PRstat.MLstat.TH

classification math.STmath.OCmath.PRstat.MLstat.TH
keywords homogenizedexacthigh-dimensionalquadraticstatisticanalyzingdatadynamics
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We develop a stochastic differential equation, called homogenized SGD, for analyzing the dynamics of stochastic gradient descent (SGD) on a high-dimensional random least squares problem with $\ell^2$-regularization. We show that homogenized SGD is the high-dimensional equivalence of SGD -- for any quadratic statistic (e.g., population risk with quadratic loss), the statistic under the iterates of SGD converges to the statistic under homogenized SGD when the number of samples $n$ and number of features $d$ are polynomially related ($d^c < n < d^{1/c}$ for some $c > 0$). By analyzing homogenized SGD, we provide exact non-asymptotic high-dimensional expressions for the generalization performance of SGD in terms of a solution of a Volterra integral equation. Further we provide the exact value of the limiting excess risk in the case of quadratic losses when trained by SGD. The analysis is formulated for data matrices and target vectors that satisfy a family of resolvent conditions, which can roughly be viewed as a weak (non-quantitative) form of delocalization of sample-side singular vectors of the data. Several motivating applications are provided including sample covariance matrices with independent samples and random features with non-generative model targets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Dimension-adapted Momentum Outscales SGD

    stat.ML 2025-05 conditional novelty 7.0 of 10

    DANA, with dimension- and time-dependent momentum, provably outscales SGD on power-law random features when 2α>1, improving loss exponents and compute-optimal curves.

Pith tools